社会科学背景下因果推论的统计方法

如何根据非随机数据估计变量间的因果关系是社会科学研究中一个迫切的方法论问题。上世纪70年代,Rubin等人指出因果问题本质上是一个反事实的问题,认为某些统计方法可保证混淆变量和分组安排独立,并将这种方法推广到观察数据的分析中。倾向分数、工具变量和回归间断点是三种常用的方法,其中倾向分数居核心地位。以实际数据为例建立计算倾向分数的logistic模型,报告了模型的整体检验、预测变量的显著性检验和多重共线性检验、建立匹配组和分析结果报告。     

基于因果模型的管理变革与信息技术研究

在本文的研究框架中,信息技术对企业产出的作用有两种路径,一种是直接作用路径,即信息技术直接提高了企业总产出,一种是间接作用路径,即信息技术促进了企业管理变革,管理变革又提高了企业总产出,也就是说管理变革是信息技术投资与企业总产出的中介变量。通过本文的研究,我们可以进一步了解信息技术投资是如何作用于企业总产出的,同时也指出企业应该进行相应地管理变革以最大化企业信息技术投资的收益。     

新建本科院校财务风险的成因及规避对策探讨

目前,财务风险已成为影响新建本科院校持续、健康发展的重要因素.该文归纳了新建本科院校财务风险客观存在的主要表现,分析了形成原因,探讨了规避对策.     

波普尔历史方法论探析

英国著名的历史哲学家波普尔提出了证伪标准论,这一科学与非科学的划界标准,成为其历史方法论的哲学基石。由此延伸开来,波普尔以猜想一反驳法为历史研究方法,其具体表现是问题境况分析法,并与柯林武德的主观重演法进行了对比。波普尔还把“试错法”的自然科学方法运用于历史研究,产生了“零碎工程学”理论。关于历史因果关系问题,波普尔主张它由普遍规律和初始条件共同作出说明。     

语言僵化的参数设置解释

语言僵化是二语习得中的一个普遍现象,也是严重制约二语发展的一个主要因素。因此,国内外许多语言学家都对语言僵化提出了自己的见解。本文主要从乔姆斯基的普遍语法理论,利用参数的设置来解释僵化的形成,提出母语参数与英语参数存在竞争关系的假说并利用实证研究证实此竞争的存在,提出参数竞争是导致僵化的原因之一。     

具有部分依从现象的临床试验中因果效应的上下界估计

在随机处理——对照的临床试验中,除出现完全依从和完全不依从的现象外,还会出现部分依从的现象,即患者只服用部分药品。在仅出现完全依从和不依从情况时,Balke and Pearl利用线性规划的方法获得了ACE估计量的上下界,对于部分依从的情况,是将这些数据全部并入完全依从的数据,这样处理的合理性没有论述。同时,利用他们所提供的方法,有时会出现下界为负数,显然,这样的下界没什么实际意义。本文根据Angrist,Imbebns＆Rubin讨论工具变量时所提出一些假设条件,导出了在部分依从情况下,计算ACE估计量的上下界的方法,并证明了其下界一定是非负的。     

Meta‐Analytic Methodology and Inferences About the Efficacy of Formative Assessment

In a recent article published in EM:IP, Kingston and Nash report on the results of a meta‐analysis on the efficacy of formative assessment. They conclude that the average effect of formative assessment on student achievement is about .20 SD units. This would seem to dispel the myth that effects between .40 and .70 can be attributed to formative assessment. They also find that there is considerable variability in effect sizes across studies, and that only the content area in which the treatment is situated explains a significant proportion of study variability. However, there are issues in the meta‐analytic methodology employed by the authors that make their findings somewhat equivocal. This commentary focuses on four methodological concerns about the Kingston and Nash meta‐analysis: (1) the approach taken to select studies for inclusion, (2) the application of study inclusion criteria, (3) the extent to which the effect sizes being combined are biased, and (4) the relationship between effect size magnitude and characteristics of outcome measures. After examining these issues in the context of the Kingston and Nash review, it appears that considerable uncertainty remains about the effect that formative assessment practices have on student achievement.     

The importance of specifying and studying causal mechanisms in school-based randomised controlled trials: lessons from two studies of cross-age peer tutoring

Based on the experience of evaluating 2 cross-age peer-tutoring interventions, we argue that researchers need to pay greater attention to causal mechanisms within the context of school-based randomised controlled trials. Without studying mechanisms, researchers are less able to explain the underlying causal processes that give rise to results from randomised controlled trials. Studying implementation fidelity is necessary but not sufficient for causal explanation; the study of causal mechanisms through the application of mixed methods is also required. Due to the increasingly complicated nature of many classroom-based innovations that are subject to evaluation, and the potentially distal nature of hypothesised effects, particularly on attainment, programme theory and articulation of mechanisms are essential in enhancing causal explanation and promoting the accumulation of knowledge of what works and why in classroom settings.     

Confirmation of a Teacher Expectancy Model: Student Perceptions and Causal Attributions of Teaching Behaviors

Abstract

This study described patterns of observed and student perceived teaching behaviors directed to high and low expectancy students and determined how students attribute causes to the teaching behaviors. Eleven certified elementary classroom teachers and their second and third-grade classes served as subjects for the study. Twenty-seven high expectancy and 33 low expectancy students were identified by having the teachers rate their students in terms of expected levels of performance for the school year. Three types of teacher feedback were recorded by trained observers: a) praise/encouragement; b) skill correction; and c) corrective behavior feedback. Students were also interviewed to see whether their perceptions of the teachers' actions were consistent with the coded dyadic interactions. In addition, interviewers asked the students to describe the causes for the teacher's actions. Each cause was classified into one of four attributional categories: a) personal causes; b) teacher causes; c) environmental causes; and d) complex causes. Major differences between observed and perceived teacher praise and corrective behavior feedback were found for high and low expectancy students. Attributional data also revealed that low expectancy students tended to attribute corrective behavior feedback to personal causes much more so than high expectancy students. High expectancy students, on the other hand, were more inclined to attribute the same behavior to teacher characteristics.     

因果必然性探析——结合休谟、卡尔纳普因果研究的考察

纵观西方因果观念的历史演变．它与必然性、决定论的相互纠缠有其特定的自然科学背景。近代．休谟提出了因果性批判;卡尔纳普试图从语义学角度来定义因果必然性。对待决定论的态度取决干不同阶段自然科学的发展状况．被认为是非（因果）决定论的量子力学却在某种意义上保留了因果必然性（微观因果性）。